Microsoft

A one-prompt attack that breaks LLM safety alignment

As LLMs and diffusion models power more applications, their safety alignment becomes critical. Our research shows that even minimal downstream fine‑tuning can weaken safeguards, raising a key question ...
Cloud Security Alliance

Logic-Layer Prompt Control Injection (LPCI): A Novel Security Vulnerability Class in Agentic Systems

Explores LPCI, a new security vulnerability in agentic AI, its lifecycle, attack methods, and proposed defenses.
IEEE

End-to-End Process Optimization in Polymer Extrusion Lines Using Model Predictive Control and Multi-Task Learning

Abstract: Due to the inherent complexity of modern polymer extrusion lines caused by nonlinear, dynamic behavior with numerous influential factors, disturbances lead to higher scrap rates and ...
IEEE

Gaussian Process-Based Prescribed-Time Input-to-State Safety for Unknown System Control

Abstract: In dynamic systems, safety is typically guaranteed through control barrier functions that keep states within a designated safe set throughout the entire evolution of the system. However, in ...